Adaptive Fuzzy Network Research Articles

A soft computing system for opencast mining machineries noise prediction

In this paper, soft computing based system models were applied to predict opencast mining machineries noise. Noise is often regarded as a nuisance rather than as an occupational hazard in an opencast mining environment. Prolonged exposure to noise over a period of years generally causes permanent damage to the auditory nerve and/or its sensory components. To maintain the good working environment in mines, appropriate noise survey of machineries should be conducted. The measured sound pressure levels (SPL) for the equipments by sound measuring devices are considered inaccurate due to instrumental error, attenuation due to geometrical aberration, atmospheric attenuation etc. Some of the popular noise prediction models e.g. ISO-9613-2, CONCAWE, VDI and ENM have been applied in mining and allied industries to predict the machineries noise by considering all the attenuation factors. Mamdani, Takagi Sugeno Kang (T-S-K) fuzzy inference system and Adaptive Network based Fuzzy inference System (ANFIS) were used to predict the machinery noise in opencast mines. From the present investigations, it was observed that the ANFIS model gave better noise prediction than the Mamdani and TSK fuzzy model

Adaptive neuro-fuzzy inference system for combined forecasts in a panel manufacturer

Improving the accuracy of demand forecasting has become a primary concern for a thin-film transistor liquid crystal display manufacturer. To address this concern, we develop a demand forecasting methodology that combines market and shipment forecasts. We investigate the weights assigned to the combination of forecasts using three linear methods (the minimum values of the forecast error, the adaptive weights and the regression analysis), as well as two nonlinear methods (fuzzy neural network and adaptive network based fuzzy inference system). A real data set from a panel manufacturer in Taiwan is used to demonstrate the application of the proposed methodology. The results show that the adaptive network based fuzzy inference system method outperforms other four methods. Also, we find that the mean absolute percent error (MAPE) of forecasting accuracy using the adaptive network based fuzzy inference system method can be improved effectively.

Fuzzy adaptive neural network approach to path loss prediction in urban areas at GSM-900 band

This paper presents the results of the Adaptive-Network Based Fuzzy Inference System (ANFIS) for the prediction of path loss in a specific urban environment. A new algorithm based ANFIS for tuning the path loss model is introduced in this work. The performance of the path loss model which is obtained from proposed algorithm is compared to the Bertoni-Walfisch model, which is one of the best studied for propagation analysis involving buildings. This comparison is based on the mean square error between predicted and measured values. According to the indicated error criterion, the errors related to the predictions that are obtained from the algorithm are less than the errors that are obtained from the Bertoni-Walfisch Model. In this study, propagation measurements were carried out in the 900 MHz band in the city of Istanbul, Turkey.

Application of fuzzy adaptive back-propagation neural network in thermal conductivity gas analyzer

Generally, industrial measuring and control system works in surroundings with rapid temperature change, and most of thermal conductivity sensor is sensitive to temperature to a certain extent. This will lead to change of the sensor's sensitivity and zero performance, so the sensor's signal output varies with the change of temperature. Besides that, the measurement error is caused by pressure and flowing of gas. Therefore, error compensation is always the key problem of industrial measuring and control system. Using neural networks to deal with this error caused by environmental factors is a low-cost and reliable method. The traditional back-propagation algorithm is simple and easy to realize. However, it also has two insurmountable defects: the most fatal one is that back-propagation algorithm is very likely to run into local minimum. The other one is its slow convergence. Thermal conductivity gas analyzer often works in adverse and dangerous surroundings, which requires a short measurement period. So, the system needs a strong anti-shock learning network. Under this condition, fuzzy adaptive regulation is adopted in learning algorithm of back-propagation, and the learning parameters are corrected automatically by expert system. A fuzzy adaptive network model with strong contraction is constructed by training of large data samples, and rapid, high-precision compensation of sensor's error is realized by the improved algorithm.

A fuzzy adaptive network approach to parameter estimation in cases where independent variables come from an exponential distribution

In a regression analysis, it is assumed that the observations come from a single class in a data cluster and the simple functional relationship between the dependent and independent variables can be expressed using the general model; Y = f ( X ) + ε . However; a data cluster may consist of a combination of observations that have different distributions that are derived from different clusters. When faced with issues of estimating a regression model for fuzzy inputs that have been derived from different distributions, this regression model has been termed the ‘switching regression model’ and it is expressed with Y L = f L ( X ) + ε L ( L = ∏ i = 1 p l i ) . Here l i indicates the class number of each independent variable and p is indicative of the number of independent variables [J.R. Jang, ANFIS: Adaptive-network-based fuzzy inference system, IEEE Transaction on Systems, Man and Cybernetics 23 (3) (1993) 665–685; M. Michel, Fuzzy clustering and switching regression models using ambiguity and distance rejects, Fuzzy Sets and Systems 122 (2001) 363–399; E.Q. Richard, A new approach to estimating switching regressions, Journal of the American Statistical Association 67 (338) (1972) 306–310]. In this study, adaptive networks have been used to construct a model that has been formed by gathering obtained models. There are methods that suggest the class numbers of independent variables heuristically. Alternatively, in defining the optimal class number of independent variables, the use of suggested validity criterion for fuzzy clustering has been aimed. In the case that independent variables have an exponential distribution, an algorithm has been suggested for defining the unknown parameter of the switching regression model and for obtaining the estimated values after obtaining an optimal membership function, which is suitable for exponential distribution.

Support Vector Fuzzy Adaptive Network in the Modeling of Material Removal Rate in Rotary Ultrasonic Machining

Rotary ultrasonic machining (RUM) is one of the cost-effective machining methods for machining difficult to process material. It is a hybrid machining process that combines the material removal mechanisms of diamond grinding with ultrasonic machining. However, due to the lack of understanding of the mechanisms of these operations, models for these machining processes are difficult to establish. In this paper, the support vector fuzzy adaptive network (SVFAN), a parameter free nonlinear regression technique, is used to model the material removal rate in RUM. The SVFAN retains the advantages of both the fuzzy adaptive networks and the support vector machines. The former possesses the linguistic representation ability and the latter is a very effective learning machine. The results are compared with that obtained by the use of fuzzy adaptive network and it is shown that the combined approach is a more effective algorithm for the modeling of complex manufacturing processes.

Support vector fuzzy adaptive network in regression analysis

Neural-fuzzy systems have been proved to be very useful and have been applied to modeling many humanistic problems. But these systems also have problems such as those of generalization, dimensionality, and convergence. Support vector machines, which are based on statistical learning theory and kernel transformation, are powerful modeling tools. However, they do not have the ability to represent and to aggregate vague and ill-defined information. In this paper, these two systems are combined. The resulting support vector fuzzy adaptive network (SVFAN) overcomes some of the difficulties of the neural-fuzzy system. To illustrate the proposed approach, a simple nonlinear function is estimated by first generating the training and testing data needed. The results show that the proposed network is a useful modeling tool.

Modelling credit rating by fuzzy adaptive network

Human judgment plays an important role in the rating of enterprise financial conditions. The recently developed fuzzy adaptive network (FAN), which can handle systems whose behaviour is influenced by human judgment, appears to be ideally suited for the modelling of this credit rating problem. In this paper, FAN is used to model the credit rating of small financial enterprises. To illustrate the approach, the data of the credit rating problem is first represented by the use of fuzzy numbers. Then, the FAN network based on inference rules is constructed. And finally, the network is trained or learned by using the fuzzy number training data. The main advantages of the proposed network are the ability for linguistic representation, linguistic aggregation and the learning ability of the neural network.

A Fuzzy Adaptive Network Model for Waviness Removal in Grinding of Wire-Sawn Silicon Wafers

Silicon is the primary semiconductor material used to fabricate microchips, and the quality of microchips depends directly upon the quality of the starting silicon wafers. One of the manufacturing problems in silicon wafer manufacturing is the presence of waviness on the surface as a result of wire-saw slicing. Various factors influence the waviness reduction capacity during soft-pad grinding; the grinding process is very complicated and difficult to define. In this research, fuzzy adaptive network, which is ideally suited to the modeling of vague phenomena, is used to model the waviness problem. Fuzzy adaptive network has the learning ability of a neural network and the linguistic representation of a complex, not well understood phenomenon. Simulation data are used to illustrate the applicability of fuzzy adaptive network. The results, even though based on some very limited data, indicate the influences of the independent parameters clearly.

Fuzzy adaptive network in presidential elections

Several scientific forecasting models for presidential elections have been suggested. However, most of these models are based on traditional statistics approaches. Since the system is linguistic, vague, and dynamic in nature, the traditional rigorous mathematical approaches are inappropriate for the modeling of this kind of humanistic system. This paper presents a combined neural fuzzy approach, namely a fuzzy adaptive network, to model and forecast the problem of a presidential election. The fuzzy adaptive network, which is ideally suited for the modeling of vaguely defined humanistic systems, combines the advantages of the representation ability of fuzzy sets and the learning ability of a neural network. To illustrate the approach, experiments were carried out by first formulating the problem, then training the network, and, finally, predicting the election results based on the trained network. The experimental results show that a fuzzy adaptive network is an ideal approach for the modeling and forecasting of national presidential elections.

Regression using fuzzy adaptive resonant theory neural network

A new neural network paradigm based on fuzzy adaptive resonant theory, which yields quantitative results, is presented. The performance of this network in building calibration models for quantitative gas analysis is estimated and compared with other well-established methods. A faster training phase and higher accuracy in regression characterise the new paradigm.

Control of rotational molding using adaptive fuzzy systems

AbstractRotational molding is a method for manufacturing hollow plastic parts. In the work reported here, adaptive fuzzy logic techniques have been used to relate the machine oven temperature to other manipulated parameters of the process. The objective is to design a reliable control system for the rotational molding process. An adaptive fuzzy network was developed to correlate changes in oven temperature to changes in the opening of the control valve on the fuel system. The network parameters were optimized using real‐valued genetic algorithms. This network gave good results when its performance was compared with experimental data from a commercial rotational molding machine. The network was successfully utilized to design a control system, which works well in regard to set point tracking and load rejection. © 2005 Wiley Periodicals, Inc. Adv Polym Techn 24: 266–277, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/adv.20047

Fuzzy adaptive networks in thermal comfort

Thermal comfort is very important in any work or operation environment. But “thermal comfort” is a very vague and not easily defined term, and it is influenced by both the physical environment and the individual’s physiology or psychology. To at least partially overcome these problems, this work proposes the use of a fuzzy adaptive network (FAN) to model the thermal comfort system. To illustrate the approach, actual experimental data were used to train the network and to give results. Although only very simple examples were used, the results show the usefulness of the proposed approach.

Fuzzy adaptive networks in machining process modelling: dimensional error prediction for turning operations

Due to the complexity of machine tool structure and the cutting process, the dynamics of machining processes are still not completely understood. This is especially true for high-speed machining processes. To model and control these complex processes, new approaches, which can represent complex phenomenon combined with learning ability, are needed. The combined neural-fuzzy approach appears ideally suited for this purpose. To illustrate the approach, the recently developed fuzzy adaptive networks are used to model dimensional error in turning operations. The fuzzy adaptive network has both the learning ability of a neural network and the linguistic representation of a complex, not well understood or vague phenomenon. An approximate model representing the influences of machining parameters on dimensional error is first established. This model is then improved by learning with the given training data. The improved models are verified by the use of test data, which are obtained by the use of actual experiments.

Fuzzy adaptive networks in machining process modeling: surface roughness prediction for turning operations

Due to the complexity of the machine tool structure and the cutting process, the dynamics of machining processes are still not completely understood. This is especially true due to the demand of high-speed machining to increase productivity. In order to model and control these complex processes, new approaches, which can represent complex phenomenon combined with learning ability, are needed. The combined neural–fuzzy approach appears to be ideally suited for this purpose. In this paper, the recently developed fuzzy adaptive network (FAN) is used to model surface roughness in turning operations. The FAN network has both the learning ability of neural network and linguistic representation of complex, not well-understood, vague phenomenon. Furthermore, it can continuously improve the initially obtained rough model based on the daily operating data. To illustrate this approach, a model representing the influences of machining parameters on surface roughness is established and then the model is verified by the use of the results of pilot experiments. Finally, a comparison with the results based on statistical regression is provided.

Sliding mode control with fuzzy adaptive perturbation compensator for 6-DOF parallel manipulator

This paper proposes a sliding mode controller with fuzzy adaptive perturbation compensator (FAPC) to get a good control performance and reduce the chatter. The proposed algorithm can reduce the chattering because the proposed fuzzy adaptive perturbation compensator compensates the perturbation terms. The compensator computes the control input for compensating unmodeled dynamic terms and disturbance by using the observer-based fuzzy adaptive network (FAN). The weighting parameters of the compensator are updated by on-line adaptive scheme in order to minimize the estimation error and the estimation velocity error of each actuator. Therefore, the combination of sliding mode control and fuzzy adaptive network gives the robust and intelligent routine to get a good control performance. To evaluate the control performance of the proposed approach, tracking control is experimentally carried out for the hydraulic motion platform which consists of a 6-DOF parallel manipulator.

Robust H∞ control of multiple time-delay uncertain nonlinear system using fuzzy model and adaptive neural network

In this paper, a robust control method which combines fuzzy model-based control with adaptive neural network control is presented for a class of uncertain nonlinear system with multiple time-delay. The fuzzy T-S model with multiple time-delay is adopted for the approximate modeling of the nonlinear system with some unknown uncertainties, and fuzzy-model-based H ∞ control law is designed by means of LMI method. A full adaptive RBF neural network is added to the fuzzy H ∞ control in order to guarantee the robust stability of the controlled system. The effect of the unknown uncertainties and the error caused by fuzzy modeling can be overcome by adaptive tuning of the weights, centers and widths of the RBF neural network on line, and no constraint or matching conditions are required. The stability of the designed closed-loop system is thus proved. The proposed method is applied to a multiple time-delay nonlinear chaotic system and the simulation results show that the proposed method cannot only stabilize the chaos systems, but has strong robustness against uncertainties and external disturbance.

Fuzzy-Art Neural Networks for Predicting Chi-Chi Earthquake Induced Liquefaction in Yuan-Lin Area

In this study, a fuzzy adaptive network “Fuzz-ART”, based on adaptive resonance theory (ART) combined with fuzzy set theory is developed to evaluate liquefaction potentials induced by Chi-Chi earthquake in Yuan-Lin area. The proposed system combines the backpropagation algorithm for parameter learning and the fuzzy ART algorithm for structure learning. With the help of case studies, it is shown that the “Fuzz-ART” network is able to predict liquefaction potentials much more satisfactorily than conventional artificial neural network methods. If more data are collected, it may well evaluate liquefaction potentials induced by Chi-Chi earthquake.

Neural network identification of high-risk suicide patients.

A history of medically serious suicide attempts (MSSA) has been considered a major risk factor for suicide. Backpropagation (BP) neural networks (NN) successfully detected patient files of patients who had committed MSSA but failed to identify MSSA patients when trained with data collected during face-to-face interviews. To develop an expert support system for the detection of suicide risk in patients with major psychiatric disorders using fuzzy adaptive learning control networks (FALCON) and BP enhanced with fuzzy logic neural networks. We used four types of input sets: (a) the most significant variables as defined by Garson's calculation of trained BP; (b) variables identified by logistic regression; (c) variables considered significant by experienced clinicians; or (d) the variables considered definitive by the computer programmer. In addition, the complete set of 59 input variables was used. The target variable was the existence of prior MSSA. Four training trials were performed with each input set (75% of the data was used for training and 25% for testing). Data was collected from 197 (50 MSSA, 147 non-MSSA) patients hospitalized at Sha'ar Menashe Mental Health Centre. BP enhanced with fuzzy logic achieved the most accurate results with the three variables chosen by the programmer (mean +/- SD; sensitivity=97% +/- 3.4%, specificity=69.2% +/- 6.9%), and FALCON trained with 15 variables chosen by an expert clinician obtained the highest sensitivity and specificity (mean +/- SD; sensitivity=94% +/- 6.9%, specificity=69% +/- 6.9%). A combined system of BP enhanced with fuzzy logic and FALCON may improve the detection rate of MSSA patients during patient interviews. A prospective validation study testing a combined system across 1, 2 and 5-year spans may provide a reliable instrument to aid in the detection of suicide prone psychiatric patients.

Neural network based analysis system for vibration analysis and condition monitoring

A system and a method for tracking long term performance of a vibrating body such as a gas turbine, includes a vibration sensor who time domain outputs are transformed to the frequency domain, using a fast Fourier transform processing. Frequency domain outputs are provided as inputs to a fuzzy adaptive resonance theory neural network. Outputs from the network can be coupled to an expert system for analysis, to display devices for presentation to an operator or are available for other control and information purposes.